Identifying Spatial Variation Patterns in Multivariate Manufacturing Processes

Large sets of multivariate measurement data are now routinely available through automated in-process measurement in many manufacturing industries. These data typically contain valuable information regarding the nature of each major source of process variability. In this article we assume that each variation source causes a distinct spatial variation pattern in the measurement data. The model that we use to represent the variation patterns is of identical structure to one widely used in the so-called “blind source separation” problem that arises in many sensor-array signal processing applications. We argue that methods developed for blind source separation can be used to identify spatial variation patterns in manufacturing data. We also discuss basic blind source separation concepts and their applicability to diagnosing manufacturing variation.     

Pairwise Estimation of Multivariate Gaussian Process Models With Replicated Observations: Application to Multivariate Profile Monitoring

Profile monitoring is often conducted when the product quality is characterized by profiles. Although existing methods almost exclusively deal with univariate profiles, observations of multivariate profile data are increasingly encountered in practice. These data are seldom analyzed in the area of statistical process control due to lack of effective modeling tools. In this article, we propose to analyze them using the multivariate Gaussian process model, which offers a natural way to accommodate both within-profile and between-profile correlations. To mitigate the prohibitively high computation in building such models, a pairwise estimation strategy is adopted. Asymptotic normality of the parameter estimates from this approach has been established. Comprehensive simulation studies are conducted. In the case study, the method has been demonstrated using transmittance profiles from low-emittance glass. Supplementary materials for this article are available online.     

Principal alarms in multivariate statistical process control using independent component analysis

This article proposes a methodology that helps to predict the main mean shifts, denoted as principal alarms, in a non-normal multivariate process using the available in-control data. The analysis is based on the transformation of the observed correlated variables into independent factors using independent component analysis. These independent components allow us to simulate shifts preserving the covariance structure. The graphical representations of those simulated shifts are helpful in improving the design and control of the process. Two real manufacturing processes are presented showing the advantage of the proposed methodology.     

Phase I Distribution-Free Analysis of Multivariate Data

In this study, a new distribution-free Phase I control chart for retrospectively monitoring multivariate data is developed. The suggested approach, based on the multivariate signed ranks, can be applied to individual or subgrouped data for detection of location shifts with an arbitrary pattern (e.g., isolated, transitory, sustained, progressive, etc.). The procedure is complemented with a LASSO-based post-signal diagnostic method for identification of the shifted variables. A simulation study shows that the method compares favorably with parametric control charts when the process is normally distributed, and largely outperforms other multivariate nonparametric control charts when the process distribution is skewed or heavy-tailed. An R package can be found in the supplementary material.     

Thresholded Multivariate Principal Component Analysis for Phase I Multichannel Profile Monitoring

Monitoring multichannel profiles has important applications in manufacturing systems improvement, but it is nontrivial to develop efficient statistical methods because profiles are high-dimensional functional data with intrinsic inner- and interchannel correlations, and that the change might only affect a few unknown features of multichannel profiles. To tackle these challenges, we propose a novel thresholded multivariate principal component analysis (PCA) method for multichannel profile monitoring. Our proposed method consists of two steps of dimension reduction: It first applies the functional PCA to extract a reasonably large number of features under the in-control state, and then uses the soft-thresholding techniques to further select significant features capturing profile information under the out-of-control state. The choice of tuning parameter for soft-thresholding is provided based on asymptotic analysis, and extensive numerical studies are conducted to illustrate the efficacy of our proposed thresholded PCA methodology.     

Alternatives to the Multivariate Control Chart for Process Dispersion

In this article, we compare the performances of six new multivariate control chart schemes for process dispersion to the standard multivariate process dispersion control chart. The six new schemes are designed by transforming the standard multivariate control chart statistic for process dispersion into a standard scale so that runs rules can be incorporated into these schemes. This article discusses a simple extension for using runs rules in a multivariate control chart for process dispersion. The extension is deemed important since the use of runs rules is always confined to univariate control charts only. The performances of the six control chart schemes together with the standard control chart are based on the computed average run length (ARL) profiles. Five of the six schemes have shown better ARL performances than the standard multivariate process dispersion control chart.     

Statistical Monitoring of a Sealing Process by Means of Multivariate Accelerometer Data

A multivariate control charting procedure is applied to on-line seal quality evaluation of a packaging process by means of an accelerometer. Based on physical insight it is elucidated in a first step which information in the raw accelerometer data are relevant with respect to the goal of detecting bad seals. Next, a principal component analysis (PCA) based processing of this multivariate information is performed and the related Hotelling's T² and Q test statistics are calculated for further data representation. In a last step proper control charts based on these statistics are used as a process monitoring tool for on-line distinction between good and bad seals. The obtained results show that a correct monitoring of accelerometer signals can be a useful tool for the on-line detection of 'bad seals' in a packaging process.     

Multivariate Statistical Process Control Based on Principal Component Analysis (MSPC-PCA): Some Reflections and a Case Study in an Autobody Assembly Process

In modern manufacturing processes, massive amounts of multivariate data are routinely collected through automated in-process sensing. These data often exhibit high correlation, rank deficiency, low signal-to-noise ratio and missing values. Conventional univariate and multivariate statistical process control techniques are not suitable to be used in these environments. This article discusses these issues and advocates the use of multivariate statistical process control based on principal component analysis (MSPC-PCA) as an efficient statistical tool for process understanding, monitoring and diagnosing assignable causes for special events in these contexts. Data from an autobody assembly process are used to illustrate the practical benefits of using MSPC-PCA rather than conventional SPC in manufacturing processes.     

统计过程控制在微电脑控制器生产中的应用:案例研究

以某电子集团生产的某类型控制器的实际生产为例,采用因果分析法对其生产过程中造成质量缺陷的原因从5M1E(人、机、料、法、测、环)方面进行综合分析.通过对其测量系统进行监控,在其稳定可靠的情况下采集数据.运用SPC技术对波峰焊工序进行控制图监控,对失控原因进行分析并在线调整.有效地保证了控制器的质量,为其质量改善指明了方向.     

A Change-Point Approach for Phase-I Analysis in Multivariate Profile Monitoring and Diagnosis

Process monitoring and fault diagnosis using profile data remains an important and challenging problem in statistical process control (SPC). Although the analysis of profile data has been extensively studied in the SPC literature, the challenges associated with monitoring and diagnosis of multichannel (multiple) nonlinear profiles are yet to be addressed. Motivated by an application in multioperation forging processes, we propose a new modeling, monitoring, and diagnosis framework for phase-I analysis of multichannel profiles. The proposed framework is developed under the assumption that different profile channels have similar structure so that we can gain strength by borrowing information from all channels. The multidimensional functional principal component analysis is incorporated into change-point models to construct monitoring statistics. Simulation results show that the proposed approach has good performance in identifying change-points in various situations compared with some existing methods. The codes for implementing the proposed procedure are available in the supplementary material.     

流程程序分析方法在印染生产线改进中的应用

以某公司的印染生产线为研究对象，运用流程程序分析方法和5W1H提问技术分析生产线存在的问题，并根据ECRS四大原则，对生产线的工艺内容、工艺方法、工艺程序和空间布置提出改进方案。     

面向半导体制造业的统计过程分析与控制

传统的统计过程控制方法不能完全适应半导体制造业生产形式需要。本文在分析半导体光电封装制造模式的特点和实施过程控制所面临的问题的基础上,提出一种基于聚类分析的统计质量控制方法。通过实证分析,证实了该方法的可操作性并取得了良好的实际效果。     

Process capability analysis in the presence of autocorrelation

Process capability analysis when observations are autocorrelated is addressed using time series modelling and regression analysis. Through the use of a numerical example, it is shown that the variance estimate obtained from the original data is no longer an appropriate estimate to be considered for conducting process capability analyses. Copyright © 2002 John Wiley & Sons, Ltd.     

冲截模CAD系统中的工艺性分析

详细论述了作者所研究开发的冲截模ＣＡＤ系统工艺性分析的基本内容，介绍了各类工艺性判别，检查了类型模型的建立，程序流程及技术要点。     

A Method for Determining Equivalence in Industrial Settings: Defining and Testing the Equivalence of Two Methods or Two Laboratories

A common practice in industrial settings is to determine the equivalence between two methods or two laboratories. Average equivalence is the preferred method. Average equivalence focuses only on the comparison of the means. However, it may be also of interest to compare the variabilities. We propose an equivalence method that considers the means and the variabilities when comparing two methods or two laboratories. We develop bounds for conducting statistical tests using the proposed equivalence criterion. Simulation is conducted to study the performance of the bounds. The criteria are the ability to maintain the stated confidence level, as well as the stated test size, and the simulated power of the tests using these bounds. Bounds that perform well for small sample size are also desirable.     

Analysis of Large Heterogeneous Repairable System Reliability Data With Static System Attributes and Dynamic Sensor Measurement in Big Data Environment

ABSTRACT

In the age of Big Data, one pressing challenge facing engineers is to perform reliability analysis for a large fleet of heterogeneous repairable systems with covariates. In addition to static covariates, which include time-invariant system attributes such as nominal operating conditions, geo-locations, etc., the recent advances of sensing technologies have also made it possible to obtain dynamic sensor measurement of system operating and environmental conditions. As a common practice in the Big Data environment, the massive reliability data are typically stored in some distributed storage systems. Leveraging the power of modern statistical learning, this article investigates a statistical approach which integrates the random forests algorithm and the classical data analysis methodologies for repairable system reliability, such as the nonparametric estimator for the mean cumulative function and the parametric models based on the nonhomogeneous Poisson process. We show that the proposed approach effectively addresses some common challenges arising from practice, including system heterogeneity, covariate selection, model specification and data locality due to the distributed data storage. The large sample properties as well as the uniform consistency of the proposed estimator are established. Two numerical examples and a case study are presented to illustrate the application of the proposed approach. The strengths of the proposed approach are demonstrated by comparison studies. Datasets and computer code have been made available on GitHub.     

疫情可视化设计中的数据分析与表达方法研究——以“重庆市新型冠状病毒肺炎疫情数据可视化分析”为例

围绕疫情数据可视化这一主题,研究如何针对突发事件的海量数据进行数据分析和可视化表达。在数据量大、内容繁杂的背景下,基于可视化设计的方法论,探讨数据可视化在突发公共卫生事件数据报道中的优势,并以“重庆市新型冠状病毒肺炎疫情数据可视化分析”设计为案例,具体分析数据可视化从设计方法到结论的过程。分析、整理适用于突发公共卫生事件下的疫情可视化设计数据分析和表达方法,为突发公共事件的设计介入、数据可视化的设计方法提供一定的补充。     

Assessment of statistical responses of multi-scale damage events in an acrylic polymeric composite to the applied stress

Assessments of the statistics of damage ensemble are essential steps to develop accurate modeling and predictions of material failures. Events of random damage constitute a damage system that resides in the microstructures of the materials. Characterization and evaluation of such a system involve assessing the evolving the cascading damage events from hierarchical microstructures of the solids, and there currently lacks an experimental means to do so. To address this need, we established an approach to acquire the events of random damage (ERD) by employing a measureable multi-variate D_A defined in our previous work based on acoustic emission. It was found that the responsive events of random damage created by pure tension and three-point bending correlated strongly across all multiscale column vectors of D_A in spacetime. The correlation strength is much stronger under tension than that under bending, and much stronger in early loading stages across the column scale vectors of the D_A variate. ERD were found to be in clear distinct statistical populations by Andrews' exploratory data analysis plots under tension and bending, and in different stages of loading, which suggests that damage mechanisms are not only “physical”, but also “statistical”. Furthermore, our data showed that the strongly coupled multiscale column vectors of D_A can be transformed orthogonally to becoming decoupled principal components, PCs, which may facilitate the constitutive modeling. However, a PC indexes nearly evenly all scale vectors of D_A, which implicates, in conjunction with the findings of correlation and Andrews' plot, can be unidirectional, bi-directional, and or interwoven, but is a complicated index variable to describe the cascading multiscale damage events in evolving hierarchical microstructures of semicrystalline polymers.